# Conditional Generation of Temporally-ordered Event Sequences

arXiv: https://arxiv.org/abs/2012.15786 · HTML: https://mlsanity.com/paper/2012.15786/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Dec 2020.

## Built on by (most cited first, 12 of 12)

- [ClarET: Pre-training a Correlation-Aware Context-To-Event Transformer for Event-Centric Generation and Classification](https://mlsanity.com/paper/2203.02225/) (2022)
- [EventBERT: A Pre-Trained Model for Event Correlation Reasoning](https://mlsanity.com/paper/2110.06533/) (2021)
- [Are Large Language Models Temporally Grounded?](https://mlsanity.com/paper/2311.08398/) (2023)
- [Analyzing Temporal Complex Events with Large Language Models? A Benchmark towards Temporal, Long Context Understanding](https://mlsanity.com/paper/2406.02472/) (2024)
- [Salience-Aware Event Chain Modeling for Narrative Understanding](https://mlsanity.com/paper/2109.10475/) (2021)
- [Go Back in Time: Generating Flashbacks in Stories with Event Temporal Prompts](https://mlsanity.com/paper/2205.01898/) (2022)
- [It's High Time: A Survey of Temporal Question Answering](https://mlsanity.com/paper/2505.20243/) (2025)
- [SubeventWriter: Iterative Sub-event Sequence Generation with Coherence Controller](https://mlsanity.com/paper/2210.06694/) (2022)
- [STORYWARS: A Dataset and Instruction Tuning Baselines for Collaborative Story Understanding and Generation](https://mlsanity.com/paper/2305.08152/) (2023)
- [Formulation Comparison for Timeline Construction using LLMs](https://mlsanity.com/paper/2403.00990/) (2024)
- [TemPrompt: Multi-Task Prompt Learning for Temporal Relation Extraction in RAG-based Crowdsourcing Systems](https://mlsanity.com/paper/2406.14825/) (2024)
- [Evaluating Temporal Reasoning in Large Language Models: Event Temporal Relation Extraction with Allen's Interval Algebra, Logical Consistency, and Relative Time in Narratives](https://mlsanity.com/paper/2610.17402/) (2026)

## Abstract (arXiv)

Models of narrative schema knowledge have proven useful for a range of event-related tasks, but they typically do not capture the temporal relationships between events. We propose a single model that addresses both temporal ordering, sorting given events into the order they occurred, and event infilling, predicting new events which fit into an existing temporally-ordered sequence. We use a BART-based conditional generation model that can capture both temporality and common event co-occurrence, meaning it can be flexibly applied to different tasks in this space. Our model is trained as a denoising autoencoder: we take temporally-ordered event sequences, shuffle them, delete some events, and then attempt to recover the original event sequence. This task teaches the model to make inferences given incomplete knowledge about the events in an underlying scenario. On the temporal ordering task, we show that our model is able to unscramble event sequences from existing datasets without access to explicitly labeled temporal training data, outperforming both a BERT-based pairwise model and a BERT-based pointer network. On event infilling, human evaluation shows that our model is able to generate events that fit better temporally into the input events when compared to GPT-2 story completion models.